INDEX

Explanations

references to mourning and honoring deceased individuals

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.19.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 AssemblyCulture

-0.68

riwal

-0.66

AndroidJUnit

-0.61

IonicModule

-0.57

ngdoc

-0.56

orianCalendar

-0.55

AccessorTable

-0.55

RegressionTest

-0.55

 autorytatywna

-0.54

gdx

-0.54

POSITIVE LOGITS

 loved

0.83

 deceased

0.83

 departed

0.80

 tragically

0.80

 beloved

0.78

 tragic

0.78

 lamented

0.71

RIP

0.71

 murdered

0.70

 killed

0.69

Activations Density 0.152%

references to mourning and honoring deceased individuals

No Comments

No Known Activations